cost_guard_check
AI agents call cost_guard_check to retrieve information from Agent Safety without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'check' operation typically queries state (Read category). Given the context of a cost guard system, this tool most likely retrieves current cost or budget information to determine if limits are exceeded. It does not modify data (no Write/Execute/Destructive semantics), nor does it involve financial transactions directly—it only monitors them.
From the tool's definition Tool named 'cost_guard_check' with 'check' verb (read-like operation) belonging to a cost monitoring tool family (cost_guard_*).
Attacks that exploit this kind of access
cost_guard_check. It is categorised as a Read tool in the Agent Safety MCP Server, which means it retrieves data without modifying state.
Register the Agent Safety MCP server in PolicyLayer and add a rule for cost_guard_check: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Agent Safety. Nothing to install.
cost_guard_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the cost_guard_check rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for cost_guard_check. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
cost_guard_check is provided by the Agent Safety MCP server (luciferforge/agent-safety-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →